Update: Taiwanese Software Spots Stock-Market Stinkers

Taiwanese computer scientists have developed a genetic algorithm one that evolves to improve its performance that can predict the impending demise or distress of publicly traded companies. The algorithm starts with 39 variables, such as sales growth rate and market value, and assigns weights to their influence. Over several iterations it optimizes the weights and then uses pattern-recognition routines to pick the losers. So far the algorithm has been tested only on Taiwanese companies, but the scientists say that it can evolve to work anywhere.